Narrow your search

Library

KBR (3)

ULiège (3)

UCLouvain (1)

UGent (1)


Resource type

book (3)


Language

English (3)


Year
From To Submit

1996 (1)

1995 (1)

1993 (1)

Listing 1 - 3 of 3
Sort by
Pattern recognition and image processing in C++
Authors: ---
ISBN: 3528054913 3322878678 9783528054915 Year: 1995 Volume: *1 Publisher: Wiesbaden : Vieweg,

Recognizing planar objects using invariant image features
Author:
ISBN: 3540567135 0387567135 3540476342 Year: 1993 Volume: vol 676 Publisher: Berlin : Springer-Verlag,

Loading...
Export citation

Choose an application

Bookmark

Abstract

Given a familiar object extracted from its surroundings, we humans have little difficulty in recognizing it irrespective of its size, position and orientation in our field of view. Changes in lighting and the effects of perspective also pose no problems. How do we achieve this, and more importantly, how can we get a computer to do this? One very promising approach is to find mathematical functions of an object's image, or of an object's 3D description, that are invariant to the transformations caused by the object's motion. This book is devoted to the theory and practice of such invariant image features, so-called image invariants, for planar objects. It gives a comprehensive summary of the field, discussing methods for recognizing both occluded and partially occluded objects, and also contains a definitive treatmentof moment invariants and a tutorial introduction to algebraic invariants, which are fundamental to affine moment invariants and to many projective invariants. A number of novel invariant functions are presented and the results of numerous experiments investigating the stability of new and old invariants are discussed. The main conclusion is that moment invariants are very effective, both for partially occluded objects and for recognizing objects in grey-level images.

Efficient visual recognition using the Hausdorff distance
Author:
ISBN: 3540619933 3540495878 Year: 1996 Volume: 1173 Publisher: Berlin [etc.] : Springer-Verlag,

Loading...
Export citation

Choose an application

Bookmark

Abstract

This book presents the theoretical aspects and practical development of a computer vision system for searching an image for a specified model object; this system is reliable, tolerates imperfections in the image and model, and is fast enough for real-world applications. A number of search techniques are evaluated. The capabilities of the author's image search system are demonstrated on a variety of examples, and applications using it to track moving objects and navigate mobile robots are shown. This book is essential reading for anybody interested in model-based object recognition.

Listing 1 - 3 of 3
Sort by